Weaviate is an open source database of the type vector search engine. Weaviate allows you to store JSON documents in a class property-like fashion while attaching machine learning vectors to these documents to represent them in vector space.
Weaviate is an open-source vector database that simplifies the development of AI applications. Built-in vector and hybrid search, easy-to-connect machine learning models, and a focus on data privacy enable developers of all levels to build, iterate, and scale AI capabilities faster.
Weaviate also supports a wide variety of OpenAI-based modules (e.g., text2vec-openai, qna-openai), allowing you to vectorize and query data fast and efficiently.
Agents Pre-built agentic workflows that dynamically interact with your data in Weaviate to perform sync, async, and multi-step tasks.
Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a cloud-native database .
Weaviate is a global remote-first startup, with teams hailing from many different parts of the world, where it is not totally uncommon for someone to work remotely from fun places.
With over 20M open source downloads and thousands of customers, Weaviate is a core piece of the stack for leading startups, scale-ups, and enterprises. "Accuracy — how good the answer is — is the first thing we want to optimize for. That’s how we found Weaviate."
Weaviate is an open-source, cloud-native vector database that stores both objects and vectors, enabling semantic search at scale. It combines vector similarity search with keyword filtering, retrieval-augmented generation (RAG), and reranking in a single query interface.